Related Experiment Video
Updated: Aug 5, 2026
12:45
Detection and Quantification of Tunneling Nanotubes Using 3D Volume View Images
Published on: August 31, 2022
Automatic Recognition and Quantification of Multiple Defects in Highway Tunnels Using Vehicle-Mounted Multisensor
Yipeng Liu1, Jianyu Hong2, Xuezeng Liu2
1College of Mechanical and Electrical Engineering, Lanzhou University of Technology, Lanzhou 730050, China.
Sensors (Basel, Switzerland)
|July 28, 2026
Summary
This study introduces an advanced multisensor system for high-speed highway tunnel inspection, enabling precise detection and measurement of multiple defects like cracks and water leakage. The innovative method ensures accurate, comprehensive assessment for intelligent tunnel maintenance.
Area of Science:
- Civil Engineering
- Computer Vision
- Geotechnical Engineering
Background:
- Intelligent inspection systems are crucial for highway tunnel maintenance.
- Existing mobile methods face challenges in balancing high-speed operation, fine-crack recognition, and multi-defect assessment.
Purpose of the Study:
- To develop an automatic recognition and quantitative assessment method for multiple visible defects in highway tunnels.
- To create a vehicle-mounted multisensor inspection system capable of high-speed, comprehensive data acquisition.
Main Methods:
- Integration of high-resolution imaging, infrared illumination, 3D laser scanning, and mileage positioning for continuous data acquisition up to 80 km/h.
- Development of a structural-feature-constrained mileage correction strategy to minimize localization errors.
- A multilevel framework for crack analysis using CNN screening, segmentation, trajectory tracking, and subpixel edge extraction for 0.1 mm-level width measurement.
- Visible-infrared image fusion and adaptive boundary refinement for water leakage and spalling detection.
- 3D tunnel axis reconstruction and point-cloud filtering for cross-sectional deformation calculation.
Main Results:
- The system enables continuous full-section data acquisition at speeds up to 80 km/h.
- Accurate recognition and quantification of multiple defects, including 0.1 mm-level crack width measurement.
- Successful identification, location, and quantification of tunnel defects in field tests and controlled experiments.
Conclusions:
- The proposed automatic recognition and quantitative assessment method provides a practical solution for intelligent highway tunnel inspection and maintenance.
- The vehicle-mounted multisensor system significantly improves the efficiency and accuracy of defect detection and assessment.
